CN102708011A - Multistage load estimating method facing task scheduling of cloud computing platform - Google Patents
Multistage load estimating method facing task scheduling of cloud computing platform Download PDFInfo
- Publication number
- CN102708011A CN102708011A CN2012101469563A CN201210146956A CN102708011A CN 102708011 A CN102708011 A CN 102708011A CN 2012101469563 A CN2012101469563 A CN 2012101469563A CN 201210146956 A CN201210146956 A CN 201210146956A CN 102708011 A CN102708011 A CN 102708011A
- Authority
- CN
- China
- Prior art keywords
- task
- average
- node
- tasks
- load
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Multi Processors (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a multistage load estimating method facing task scheduling of a cloud computing platform. The method provided by the invention fully considers dynamic variation of own loads of task nodes, difference in performance of different task nodes and difference in different task load needs, selects operation queue average progress number, average CPU (central processing unit) utilization ration, average memory utilization ratio and average network bandwidth utilization ratio as load parameters for estimating, and gives different priorities to load parameters, so that a multistage load estimating method is provided for task scheduling of a large-scale server cluster. An adaptive task scheduling method of the cloud computing platform further is disclosed by the invention. Compared with the prior art, the method provided by the invention has the advantages of high precision and low consumption, and fully meets demands on task scheduling policies of the cloud computing platform.
Description
Technical field
The present invention relates to a kind of load evaluation method, be mainly used in the load evaluation of realizing clustered node in the cloud computing platform task scheduling, belong to technical field of the computer network.
Background technology
Cloud computing (Cloud Computing) is the focus of present computer realm research, has advantages such as enhanced scalability and high availability.Cloud computing platform is deployed on the extensive server cluster, for cloud computing provides reliable computing power.In extensive server cluster, be responsible for the scheduling of operation and the distribution node of task and be called management node; The concrete clustered node of carrying out of the task of being responsible for is called task node.
Cloud computing platform is subject to task node Limited resources and computing power when the scheduling of the task of realization, can not unconfined allocating task.But a kind of effectively and simply method is through setting the task sum of task node maximum executed in parallel.But possibly cause taking place following two kinds of situation:
(1) if task node belongs to the high-performance calculation node; When but the number of executing the task has equaled the maximum executing tasks parallelly and counts, this task node will have no right to continue to obtain task, and this moment; If the load of this task node is still lighter; Show and also have the ability to carry out more task, will produce " hunger " phenomenon like this, cause the waste of idling-resource.
(2) if task node belongs to the low performance computing node, but when the number of executing the task was counted less than the maximum executing tasks parallelly, this task node was with the continuation application new task; And this moment; If the load of this task node is very heavy, show that impotentia is carried out more task, " saturated " phenomenon will appear; Cause the node machine of delaying, catastrophic failure takes place.
This not only influences the performance of cluster to a great extent, also can cause the waste of cluster resource.Consider dynamic change, the difference of different task joint behavior and the difference of different task loading demand of task node self actual loading, but a kind of reliable more and high-efficiency method is based on the number of tasks that the dynamic load self-adaptation is regulated the maximum executed in parallel.Therefore, the load size of clustered node being made rational assessment is the prerequisite that realizes efficient, reliable task scheduling strategy.
Summary of the invention
Technical matters to be solved by this invention is to overcome the deficiency that existing cloud computing platform load evaluation mechanism exists; A kind of multistage load evaluation method towards the cloud computing platform task scheduling is provided; When improving the load evaluation precision as far as possible, reduce the system overhead that load evaluation method itself is brought.
The present invention is concrete to adopt following technical scheme to solve the problems of the technologies described above.
A kind of multistage load evaluation method towards the cloud computing platform task scheduling may further comprise the steps:
Steps A, task node calculate in the current collection period the average process number of operation queue of self, and count saturation threshold with preset process and compare: count saturation threshold like the average process number＜process of operation queue, go to step B; Otherwise, judge that this task node is in saturated mode, i.e. load exceeds tolerance range;
Step B, task node calculate in the current collection period average cpu busy percentage and the average memory usage of self; And respectively with preset cpu busy percentage saturation threshold; The memory usage saturation threshold compares: like average cpu busy percentage＜cpu busy percentage saturation threshold; And average memory usage＜memory usage saturation threshold is then changeed step C; Otherwise, judge that this task node is in saturated mode;
Step C, task node calculate in the current collection period averaging network bandwidth availability ratio of self, and compare with preset network bandwidth utilization factor saturation threshold: like averaging network bandwidth availability ratio＜network bandwidth utilization factor saturation threshold, then change
Step D; Otherwise, judge that this task node is in saturated mode;
Step D, the average process number of operation queue, average cpu busy percentage, average memory usage, averaging network bandwidth availability ratio are counted optimal threshold, cpu busy percentage optimal threshold, memory usage optimal threshold, network bandwidth utilization factor optimal threshold relatively with the process that is provided with in advance respectively; Wherein, Process is counted optimal threshold＜process and is counted saturation threshold; Cpu busy percentage optimal threshold＜cpu busy percentage saturation threshold; Memory usage optimal threshold＜memory usage saturation threshold; Network bandwidth utilization factor optimal threshold＜network bandwidth utilization factor saturation threshold: when the average process number＜process of operation queue is counted optimal threshold, average cpu busy percentage＜cpu busy percentage optimal threshold, average memory usage＜memory usage optimal threshold, and＜network bandwidth utilization factor optimal threshold is met simultaneously, judges that then this task node is in hungry attitude; Be that load is lighter, can continue to bear new task; Otherwise, judge that this task node is in optimum attitude, promptly load is reasonable.
The present invention chooses the average process number of operation queue, average cpu busy percentage, on average memory usage, averaging network bandwidth availability ratio are mainly considered based on following as the required load parameter of assessment:
(1) the average process number of operation queue: the scheduler of server can constantly let the task run in the formation; But when task queue is long; Because each task possibly make CPU be in not responsive state to the competition of resource, this moment, node was in the duty of overload.The generation of this situation can be effectively avoided in the selection of the average process number of operation queue.
(2) average cpu busy percentage, average memory usage: there are a plurality of carrying out of tasks in task queue; Average cpu busy percentage and average memory usage can reflect the size of the occupying system resources of executing the task reliably, judge that present node has or not enough big resource to go to carry out new task.
(3) averaging network bandwidth availability ratio: the size of reflection node bandwidth load, judge that present node has or not enough network bandwidths to accept to receive new task.If do not consider the factor of the network bandwidth, can cause the generation of network congestion phenomenon.
The present invention has also set different priority for selected load parameter; Load parameter when high priority>during preset threshold values; Judge that this task node is in saturated mode, need not to gather again the load parameter of lower priority, can effectively reduce system overhead like this.
Further; The average process number of operation queue in the said current collection period, average cpu busy percentage, average memory usage, averaging network bandwidth availability ratio; Obtain according to following method: in current collection period, repeatedly read corresponding system kernel file in this task node; Obtain one group of operation queue process number, cpu busy percentage, memory usage, network bandwidth utilization factor, get its mean value then respectively.
According to invention thinking of the present invention, also can obtain a kind of cloud computing platform self-adapting task scheduling method, may further comprise the steps:
Step 2, each task node are carried out dynamic-configuration according to self load condition and the number of tasks of carrying out in k heart beat cycle continuously to task, k for preset greater than 1 natural number, the concrete configuration method is following:
When the load condition in a continuous k heart beat cycle occurring all is in hungry attitude, but as if the number of tasks of the number of tasks of carrying out less than current maximum executed in parallel, but then the number of tasks of maximum executed in parallel is not adjusted; Otherwise, but the number of tasks of maximum executed in parallel is increased;
When the load condition in a continuous k heart beat cycle occurring all is in saturated mode, at first kills overtime not meeting with a response of task, and this task is reported to management node, the request management node redistributes this task to suitable task node; But judge the number of tasks carrying out then whether less than the number of tasks of current maximum executed in parallel, in this way, but then the number of tasks of maximum executed in parallel is adjusted into the number of tasks of carrying out; As not, but then the number of tasks of maximum executed in parallel is reduced; In other cases, do not take any measure;
Step 3, each task node are according to heart beat cycle repeated execution of steps 1, step 2.
But the number of tasks with the maximum executed in parallel described in the step 2 of such scheme increases/reduces, and can confirm the numerical value increase at every turn/reduce according to actual conditions, but the present invention preferably adds/subtract 1 with the number of tasks of current maximum executed in parallel.
Compare prior art, the present invention has following beneficial effect:
(1) the load evaluation result accurately and reliably.For the load actual overhead of node, the present invention proposes complete system evaluation model and come the analysis node state.For the shake of avoidance system performance, influence the accuracy and the precision of acquisition node information, introduced load information formation method, the load average in the timing statistics section is dynamically held the overall process that the node task is carried out.
(2) in order to evade the huge pressure that traditional assessment models " collection mechanism " is brought to management node, the present invention takes task node " assessment voluntarily, management voluntarily " Policy evaluation method, assess real-timely, can Real-time and Dynamic hold the node load variation.
(3) high assessment precision, low assessment system overhead.The load information that the present invention gathered all is to obtain through the reading system kernel file, so can not produce excessive system overhead.
(4) the present invention can realize task node variation according to load in the process of operation, obtains task according to computing power, realizes each node self-adapting adjusting; Task scheduling algorithm of the present invention has good speed-up ratio, the T.T. of effectively minimizing task response.
Description of drawings
Fig. 1 is the system architecture synoptic diagram of cloud computing platform;
Fig. 2 is the process flow diagram of multistage load evaluation method of the present invention;
Fig. 3 is the state exchange synoptic diagram of task node;
Fig. 4 is the schematic flow sheet of cloud computing platform self-adapting task scheduling method of the present invention.
Embodiment
Below in conjunction with accompanying drawing technical scheme of the present invention is elaborated:
Thinking of the present invention is to consider from aspects such as the average process number of the operation queue of clustered node, CPU and memory usage, network bandwidth utilization factors, adopts multistage load evaluation method, realizes the high efficiency and the reliability of clustered node load evaluation.
1, assessment models
(1) nodal analysis method
The clustered node of cloud computing platform; Be divided into two types from function: management node (Master Node) and task node (Task Node); As shown in Figure 1; After cloud computing platform is submitted in operation, be responsible for operation is cut into by management node and select suitable task node deployment task after several tasks.Node definition is following:
Define 1 management node (Master Node), the management node of cloud computing platform is responsible for the management of whole group system and the scheduling of task.
Define 2 task nodes (Task Node), the task node of cloud computing platform is responsible for task executions.
(2) load module
Task node is carried out rational load evaluation, realize task node result according to load evaluation in the process of operation, but dynamic adjustments maximum executing tasks parallelly number is realized obtaining task according to computing power.Avoid huge pressure simultaneously because of adopting the complex schedule algorithm that management node is brought.According to above-mentioned requirements, the present invention introduces the notion of load priority, at first chooses the load parameter of operation queue average length (LoadAverage) as high priority, and it has reacted the average process number in the operation queue in specified time interval; Secondly, choose cpu busy percentage (CpuUsage) and memory usage (MemoryUsage) load parameter as medium priority, they have reacted the size of current operation task occupying system resources; At last, choose the load parameter of network bandwidth utilization factor (NetworkBandwidthUsage) as low priority, it is an important indicator weighing the network operating position, embodies the size of present node offered load.Each load parameter defines as follows:
Define 3 operation queue average lengths (LoadAverage, LA), the average process number of the operation queue in certain period.
Definition 4CPU utilization factor (CpuUsage, CU), the average cpu busy percentage in the current collection period.
Define 5 memory usages (MemoryUsage, MU), the average memory usage in the current collection period.
Define 6 network bandwidth utilization factors (NetworkBandwidthUsage, NBU), the average bandwidth utilization factor in the current collection period.
(3) state model
According to above-mentioned three grades of loading index, the current system overhead that has used of statistics task node.According to the size of expense, for task node defines current state of living in.Among the present invention node is divided into three kinds of states, each task node all possibly be in one of following three kinds of states:
(hungry attitude, HUNGER): the load of task node is lighter, can continue to bear new task for state A.
State B (optimum attitude, OPTIMAL): the load of task node is reasonable, and current executing tasks parallelly number is reasonable.
State C (saturated mode, SATURATION): the load of task node is heavier, and current executing tasks parallelly number exceeds tolerance range.
In order to describe the attribute with the decision node state, among the present invention for each load parameter defined respectively optimal threshold (OptimalValue, OV) and saturation threshold (ThresholdValue, TV), optimal threshold is less than saturation threshold.Each load parameter of current task node is during all less than corresponding optimal value, and this node is in " hungry attitude "; Arbitrary load parameter of current task node is during greater than corresponding saturation threshold, and this node is in " saturated mode "; Under other situation, node is in " optimum attitude ".
Shake for fear of system performance; Influence the accuracy and the precision of acquisition node information; The present invention has introduced the load information formation, comprising: operation queue average length, cpu busy percentage, memory usage, network bandwidth utilization factor (LoadAverageQueue, CpuQueue, MemoryQueue, NetworkBandwidthQueue).Each task node is safeguarded the load information formation that length is N, when getting into next collection period, and acquisition node information again, the data of one-period in the replacement.
Be that example is come technical scheme of the present invention is described with the cloud computing platform that adopts linux system below: the multistage load evaluation method towards the cloud computing platform task scheduling of the present invention, as shown in Figure 2, according to following steps:
Step 1: initialization correlation parameter: comprise optimal threshold (OV), the saturation threshold (TV) of each load parameter, and load information queue length N, OV
1-OV
4, TV
1-TV
4Represent operation queue average length, cpu busy percentage, memory usage, the optimal threshold of network bandwidth utilization factor, saturation threshold respectively;
Step 2: in collection period, at first obtain one group of operation queue process number, and it is write load information formation LoadAverageQueue through reading system kernel file/proc/loadavg repeatedly;
Step 3: the average process of operation queue according to load information formation LoadAverageQueue calculates in the current collection period is counted LA, that is:
Judge the LA size, if LA<tV
1, then get into step 4, otherwise jump to step 8;
Step 4: through reading system kernel file/proc/stat repeatedly and/proc/meminfo, obtain one group of cpu busy percentage and one group of memory usage, and write load information formation CpuQueue and MemoryQueue respectively respectively;
Step 5: calculate average cpu busy percentage CU and memory usage MU in the current collection period according to load queue CpuQueue and MemoryQueue, that is:
Judge CU and MU size, if CU<tV
2And MU<tV
3, then get into step 6, otherwise jump to step 8;
Step 6: obtain a group network bandwidth availability ratio through reading system kernel file/proc/net/dev repeatedly, write load information formation NetworkBandwidthQueue;
Step 7: calculate the averaging network bandwidth availability ratio NBU in the current collection period according to load queue NetworkBandwidthQueue, that is:
IF(LA>=TV
1||CU>=TV
2||BU>=TV
3||NBU>=TV
4)
STATE=SATURATION
ELSE?IF(LA<OV
1&&CU<OV
2&&BU<OV
3&&NBU<OV
4)
STATE=HUNGER
ELSE?STATE=OPTIMAL
Pass through said process; Each task node has been realized the load condition of self is accurately assessed, according to this assessment result, and can be as shown in Figure 3; The correlation parameter of task node and the task of node are carried out the self-adaptation adjustment; Make each task node be in optimum attitude as far as possible, thereby reduce the waste of cluster resource, improve the performance of cluster.Cloud computing platform self-adapting task scheduling method in this embodiment (Adaptive Task Scheduling is called for short ATS), its flow process is as shown in Figure 4, specifically may further comprise the steps:
Step 1: but the number of tasks (MaxTasksCapacity) of each task node initialization maximum executed in parallel, two load variables (OverLoadStatusCount, LightLoadStatusCount), load condition metering cycle k;
Step 2: each task node number of tasks (RunningTasks) that (HeartBeatTime) calculation task node is being carried out in heart beat cycle, adopt load evaluation method of the present invention to carry out load evaluation simultaneously; In this heart beat cycle, if STATE is hungry attitude, then the LightLoadStatusCount value adds 1, simultaneously with the OverLoadStatusCount zero clearing; If STATE is a saturated mode, then the OverLoadStatusCount value adds 1, simultaneously with the LightLoadStatusCount zero clearing; If STATE is optimum attitude, simultaneously with LightLoadStatusCount and OverLoadStatusCount zero clearing;
Step 3: after task node reaches heart time; Whether result (STATE) decision according to RunningTasks, MaxTasksCapacity and load evaluation asks for new task to management node; If RunningTasks is < when MaxTasksCapacity and this task node are in hungry attitude or optimum attitude; Putting AskForNewTask is TRUE, asks for task to management node; Otherwise putting AskForNewTask is FALSE, does not ask for new task to management node;
Step 4: relatively the load variable (OverLoadStatusCount, LightLoadStatusCount) and the relation between the load variable threshold value k, specific as follows:
(1), work as LightLoadStatusCount==k, show that the load condition in the continuous k heart beat cycle all is in hungry attitude, if RunningTasks MaxTasksCapacity, the value of then putting MaxTasksCapacity remains unchanged; Otherwise put MaxTasksCapacity=RunningTasks+ 1; To compare load variable (OverLoadStatusCount, LightLoadStatusCount) all zero clearings;
(2), work as OverLoadStatusCount==k; Show that the load condition in the continuous k heart beat cycle all is in saturated mode; Kill overtime not meeting with a response of task, and this task is reported to management node, the request management node is redistributed to suitable task node this task; < MaxTasksCapacity then puts MaxTasksCapacity=RunningTasks as if RunningTasks; Otherwise put MaxTasksCapacity=MaxTasksCapacity-1; To compare load variable (OverLoadStatusCount, LightLoadStatusCount) all zero clearings.
(3), (OverLoadStatusCount LightLoadStatusCount) is not equal to k, does not then take any measure, and task node is further monitored the conversion of own load when two load variables;
Step 5: task node sends heartbeat packet with HeartBeatTime time cycle property ground to management node; Change step 2, carry out round-robin scheduling.
Claims (4)
1. the multistage load evaluation method towards the cloud computing platform task scheduling is characterized in that, may further comprise the steps:
Steps A, task node calculate in the current collection period the average process number of operation queue of self, and count saturation threshold with preset process and compare: count saturation threshold like the average process number＜process of operation queue, go to step B; Otherwise, judge that this task node is in saturated mode, i.e. load exceeds tolerance range;
Step B, task node calculate in the current collection period average cpu busy percentage and the average memory usage of self; And respectively with preset cpu busy percentage saturation threshold; The memory usage saturation threshold compares: like average cpu busy percentage＜cpu busy percentage saturation threshold; And average memory usage＜memory usage saturation threshold is then changeed step C; Otherwise, judge that this task node is in saturated mode;
Step C, task node calculate in the current collection period averaging network bandwidth availability ratio of self, and compare with preset network bandwidth utilization factor saturation threshold: like averaging network bandwidth availability ratio＜network bandwidth utilization factor saturation threshold, then change step D; Otherwise, judge that this task node is in saturated mode;
Step D, the average process number of operation queue, average cpu busy percentage, average memory usage, averaging network bandwidth availability ratio are counted optimal threshold, cpu busy percentage optimal threshold, memory usage optimal threshold, network bandwidth utilization factor optimal threshold relatively with the process that is provided with in advance respectively; Wherein, Process is counted optimal threshold＜process and is counted saturation threshold; Cpu busy percentage optimal threshold＜cpu busy percentage saturation threshold; Memory usage optimal threshold＜memory usage saturation threshold; Network bandwidth utilization factor optimal threshold＜network bandwidth utilization factor saturation threshold: when the average process number＜process of operation queue is counted optimal threshold, average cpu busy percentage＜cpu busy percentage optimal threshold, average memory usage＜memory usage optimal threshold, and＜network bandwidth utilization factor optimal threshold is met simultaneously, judges that then this task node is in hungry attitude; Be that load is lighter, can continue to bear new task; Otherwise, judge that this task node is in optimum attitude, promptly load is reasonable.
2. according to claim 1 towards the multistage load evaluation method of cloud computing platform task scheduling; It is characterized in that; The average process number of operation queue in the said current collection period, average cpu busy percentage, average memory usage, averaging network bandwidth availability ratio; Obtain according to following method: in current collection period, repeatedly read corresponding system kernel file in this task node; Obtain one group of operation queue process number, cpu busy percentage, memory usage, network bandwidth utilization factor, get its mean value then respectively.
3. a cloud computing platform self-adapting task scheduling method is characterized in that, may further comprise the steps:
Step 1, each task node calculate the number of tasks that this task node is being carried out in current heart beat cycle, adopt claim 1 or 2 said load evaluation methods to carry out load evaluation simultaneously; When current heart beat cycle finishes, but the number of tasks of carrying out like this task node less than the number of tasks of the maximum executed in parallel of this task node, and its state is hungry attitude or optimum attitude, then asks for task to management node; Otherwise, do not ask for task to management node;
Step 2, each task node are carried out dynamic-configuration according to self load condition and the number of tasks of carrying out in k heart beat cycle continuously to task, k for preset greater than 1 natural number, the concrete configuration method is following:
When the load condition in a continuous k heart beat cycle occurring all is in hungry attitude, but as if the number of tasks of the number of tasks of carrying out less than current maximum executed in parallel, but then the number of tasks of maximum executed in parallel is not adjusted; Otherwise, but the number of tasks of maximum executed in parallel is increased;
When the load condition in a continuous k heart beat cycle occurring all is in saturated mode, at first kills overtime not meeting with a response of task, and this task is reported to management node, the request management node redistributes this task to suitable task node; But judge the number of tasks carrying out then whether less than the number of tasks of current maximum executed in parallel, in this way, but then the number of tasks of maximum executed in parallel is adjusted into the number of tasks of carrying out; As not, but then the number of tasks of maximum executed in parallel is reduced;
In other cases, do not take any measure;
Step 3, each task node are according to heart beat cycle repeated execution of steps 1, step 2.
4. like the said cloud computing platform self-adapting task scheduling method of claim 3, it is characterized in that, but described in the step 2 number of tasks of maximum executed in parallel is increased/reduces, but be meant that specifically the number of tasks with current maximum executed in parallel adds/subtract 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210146956.3A CN102708011B (en) | 2012-05-11 | 2012-05-11 | Adaptive task scheduling method of cloud computing platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210146956.3A CN102708011B (en) | 2012-05-11 | 2012-05-11 | Adaptive task scheduling method of cloud computing platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102708011A true CN102708011A (en) | 2012-10-03 |
| CN102708011B CN102708011B (en) | 2014-03-26 |
Family
ID=46900825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210146956.3A Expired - Fee Related CN102708011B (en) | 2012-05-11 | 2012-05-11 | Adaptive task scheduling method of cloud computing platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102708011B (en) |
Cited By (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103105923A (en) * | 2013-03-07 | 2013-05-15 | 鄂尔多斯市云泰互联科技有限公司 | Energy-efficient scheduling method and system for information technology (IT) business of cloud computing center |
| CN103226467A (en) * | 2013-05-23 | 2013-07-31 | 中国人民解放军国防科学技术大学 | Data parallel processing method and system as well as load balancing scheduler |
| CN103327093A (en) * | 2013-06-17 | 2013-09-25 | 苏州市职业大学 | Method for controlling cloud computing system |
| CN103685569A (en) * | 2013-12-31 | 2014-03-26 | 曙光云计算技术有限公司 | Method and system for automatically adjusting resource pool |
| CN103746838A (en) * | 2013-12-26 | 2014-04-23 | 华北计算技术研究所 | Task scheduling method of computer network without center node |
| CN103902379A (en) * | 2012-12-25 | 2014-07-02 | 中国移动通信集团公司 | Task scheduling method and device and server cluster |
| CN103902364A (en) * | 2012-12-25 | 2014-07-02 | 腾讯科技（深圳）有限公司 | Physical resource management method and device and intelligent terminal |
| CN104142862A (en) * | 2013-12-16 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Overload protection method and device for server |
| CN104182278A (en) * | 2013-05-23 | 2014-12-03 | 华为技术有限公司 | Method and device for judging busy degree of computer hardware resource |
| WO2015196885A1 (en) * | 2014-06-27 | 2015-12-30 | 阿里巴巴集团控股有限公司 | Method and apparatus for acquiring and storing performance data of cloud computing system |
| CN105323106A (en) * | 2014-08-04 | 2016-02-10 | 中兴通讯股份有限公司 | Software upgrade management method, equipment and system |
| CN105491138A (en) * | 2015-12-15 | 2016-04-13 | 国网智能电网研究院 | Load rate based graded triggering distributed load scheduling method |
| CN105516317A (en) * | 2015-12-14 | 2016-04-20 | 北京科东电力控制系统有限责任公司 | Multi-level load equalization efficient collection method for power utilization information |
| CN105577760A (en) * | 2015-12-16 | 2016-05-11 | 南京邮电大学 | Cloud calculation graded management method and system |
| CN106155802A (en) * | 2015-03-30 | 2016-11-23 | 阿里巴巴集团控股有限公司 | Method for scheduling task, device and control node |
| CN106713396A (en) * | 2015-11-17 | 2017-05-24 | 阿里巴巴集团控股有限公司 | Server scheduling method and system |
| CN106844027A (en) * | 2017-01-13 | 2017-06-13 | 广西电网有限责任公司电力科学研究院 | A kind of method for scheduling task based on node load |
| CN107562537A (en) * | 2017-08-21 | 2018-01-09 | 中南大学 | A kind of cloud computing method for scheduling task based on gravitation search |
| CN108241534A (en) * | 2016-12-27 | 2018-07-03 | 阿里巴巴集团控股有限公司 | A kind of task processing, distribution, management, the method calculated and device |
| CN105718364B (en) * | 2016-01-15 | 2018-07-17 | 西安交通大学 | Resource capability dynamic assessment method is calculated in a kind of cloud computing platform |
| CN108664326A (en) * | 2017-03-28 | 2018-10-16 | 富士通株式会社 | Information processing equipment and information processing system |
| US10114672B2 (en) | 2013-12-31 | 2018-10-30 | Thomson Licensing | User-centered task scheduling for multi-screen viewing in cloud computing environment |
| CN109445918A (en) * | 2018-10-17 | 2019-03-08 | Oppo广东移动通信有限公司 | Method for scheduling task, device, terminal and storage medium |
| CN109614228A (en) * | 2018-11-27 | 2019-04-12 | 南京轨道交通系统工程有限公司 | Comprehensively monitoring front-end system and working method based on dynamic load leveling mode |
| CN110196768A (en) * | 2018-03-22 | 2019-09-03 | 腾讯科技（深圳）有限公司 | The method and apparatus for automatically determining the loading level of cloud platform resource |
| CN110348681A (en) * | 2019-06-04 | 2019-10-18 | 国网浙江省电力有限公司衢州供电公司 | A kind of electric power CPS dynamic load distribution method |
| CN110365765A (en) * | 2019-07-11 | 2019-10-22 | 网宿科技股份有限公司 | A kind of bandwidth scheduling method and device of cache server |
| CN111711575A (en) * | 2020-03-18 | 2020-09-25 | 宁波送变电建设有限公司永耀科技分公司 | Distributed multi-station fusion system fault diagnosis and flow dynamic scheduling method |
| CN112003660A (en) * | 2020-07-17 | 2020-11-27 | 北京大学深圳研究生院 | Dimension measurement method of resources in network, calculation force scheduling method and storage medium |
| CN112035236A (en) * | 2020-09-08 | 2020-12-04 | 深圳天源迪科信息技术股份有限公司 | Task scheduling method, device and storage medium based on multi-factor cooperation |
| CN112328383A (en) * | 2020-11-19 | 2021-02-05 | 湖南智慧畅行交通科技有限公司 | Priority-based job concurrency control and scheduling algorithm |
| CN112394803A (en) * | 2020-11-25 | 2021-02-23 | 超越科技股份有限公司 | Domestic server power consumption real-time dynamic adjusting method |
| CN112738146A (en) * | 2019-10-28 | 2021-04-30 | 杭州海康威视系统技术有限公司 | Access node equipment, access system, equipment scheduling method and equipment scheduling device |
| CN112788099A (en) * | 2020-11-11 | 2021-05-11 | 中移雄安信息通信科技有限公司 | Method, device and equipment for loading back-end service and computer storage medium |
| CN112835773A (en) * | 2019-11-25 | 2021-05-25 | 合肥欣奕华智能机器有限公司 | Method and device for evaluating real-time performance of task running in operating system |
| CN113159957A (en) * | 2021-05-17 | 2021-07-23 | 深圳前海微众银行股份有限公司 | Transaction processing method and device |
| CN113434267A (en) * | 2021-05-25 | 2021-09-24 | 深圳大学 | Cloud computing workflow dynamic scheduling method, device, equipment and storage medium |
| CN116151137A (en) * | 2023-04-24 | 2023-05-23 | 之江实验室 | Simulation system, method and device |
| CN116341991A (en) * | 2023-05-29 | 2023-06-27 | 江苏智慧优视电子科技有限公司 | Heavy-duty truck power conversion cloud service system and method based on cloud computing |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662763A (en) * | 2012-04-11 | 2012-09-12 | 华中科技大学 | Virtual machine resource scheduling method based on service quality |
-
2012
- 2012-05-11 CN CN201210146956.3A patent/CN102708011B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662763A (en) * | 2012-04-11 | 2012-09-12 | 华中科技大学 | Virtual machine resource scheduling method based on service quality |
Non-Patent Citations (2)
| Title |
|---|
| 《计算机技术与发展》 20100531 卢照 等 MPI动态负载平衡策略的研究与实现 132-134 3,4 第20卷, 第5期 * |
| 卢照 等: "MPI动态负载平衡策略的研究与实现", 《计算机技术与发展》 * |
Cited By (61)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902379A (en) * | 2012-12-25 | 2014-07-02 | 中国移动通信集团公司 | Task scheduling method and device and server cluster |
| CN103902364B (en) * | 2012-12-25 | 2018-10-30 | 腾讯科技（深圳）有限公司 | A kind of physical resource management method, apparatus and intelligent terminal |
| CN103902364A (en) * | 2012-12-25 | 2014-07-02 | 腾讯科技（深圳）有限公司 | Physical resource management method and device and intelligent terminal |
| CN103105923A (en) * | 2013-03-07 | 2013-05-15 | 鄂尔多斯市云泰互联科技有限公司 | Energy-efficient scheduling method and system for information technology (IT) business of cloud computing center |
| CN103105923B (en) * | 2013-03-07 | 2015-05-27 | 鄂尔多斯市云泰互联科技有限公司 | Energy-efficient scheduling method and system for information technology (IT) business of cloud computing center |
| CN104182278B (en) * | 2013-05-23 | 2018-03-13 | 华为技术有限公司 | A kind of method and apparatus for judging computer hardware resource busy extent |
| CN104182278A (en) * | 2013-05-23 | 2014-12-03 | 华为技术有限公司 | Method and device for judging busy degree of computer hardware resource |
| CN103226467A (en) * | 2013-05-23 | 2013-07-31 | 中国人民解放军国防科学技术大学 | Data parallel processing method and system as well as load balancing scheduler |
| CN103327093B (en) * | 2013-06-17 | 2016-04-27 | 苏州市职业大学 | The control method of cloud computing system |
| CN103327093A (en) * | 2013-06-17 | 2013-09-25 | 苏州市职业大学 | Method for controlling cloud computing system |
| CN104142862A (en) * | 2013-12-16 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Overload protection method and device for server |
| WO2015090248A1 (en) * | 2013-12-16 | 2015-06-25 | 腾讯科技（深圳）有限公司 | Server overload protection method and device |
| CN104142862B (en) * | 2013-12-16 | 2015-09-16 | 腾讯科技（深圳）有限公司 | The overload protection method of server and device |
| CN103746838A (en) * | 2013-12-26 | 2014-04-23 | 华北计算技术研究所 | Task scheduling method of computer network without center node |
| CN103746838B (en) * | 2013-12-26 | 2016-12-07 | 华北计算技术研究所 | A kind of method for scheduling task of non-stop layer node computer network |
| CN103685569A (en) * | 2013-12-31 | 2014-03-26 | 曙光云计算技术有限公司 | Method and system for automatically adjusting resource pool |
| US10114672B2 (en) | 2013-12-31 | 2018-10-30 | Thomson Licensing | User-centered task scheduling for multi-screen viewing in cloud computing environment |
| WO2015196885A1 (en) * | 2014-06-27 | 2015-12-30 | 阿里巴巴集团控股有限公司 | Method and apparatus for acquiring and storing performance data of cloud computing system |
| CN105242873A (en) * | 2014-06-27 | 2016-01-13 | 阿里巴巴集团控股有限公司 | Method and apparatus for acquiring and storing performance data of cloud computing system |
| CN105242873B (en) * | 2014-06-27 | 2018-06-01 | 阿里巴巴集团控股有限公司 | The acquisition of the performance data of cloud computing system and storage method and device |
| CN105323106A (en) * | 2014-08-04 | 2016-02-10 | 中兴通讯股份有限公司 | Software upgrade management method, equipment and system |
| CN106155802B (en) * | 2015-03-30 | 2020-03-13 | 阿里巴巴集团控股有限公司 | Task scheduling method and device and control node |
| CN106155802A (en) * | 2015-03-30 | 2016-11-23 | 阿里巴巴集团控股有限公司 | Method for scheduling task, device and control node |
| CN106713396B (en) * | 2015-11-17 | 2021-07-16 | 阿里巴巴集团控股有限公司 | Server scheduling method and system |
| CN106713396A (en) * | 2015-11-17 | 2017-05-24 | 阿里巴巴集团控股有限公司 | Server scheduling method and system |
| CN105516317A (en) * | 2015-12-14 | 2016-04-20 | 北京科东电力控制系统有限责任公司 | Multi-level load equalization efficient collection method for power utilization information |
| CN105491138A (en) * | 2015-12-15 | 2016-04-13 | 国网智能电网研究院 | Load rate based graded triggering distributed load scheduling method |
| CN105491138B (en) * | 2015-12-15 | 2020-01-24 | 国网智能电网研究院 | Distributed load scheduling method based on load rate graded triggering |
| CN105577760A (en) * | 2015-12-16 | 2016-05-11 | 南京邮电大学 | Cloud calculation graded management method and system |
| CN105718364B (en) * | 2016-01-15 | 2018-07-17 | 西安交通大学 | Resource capability dynamic assessment method is calculated in a kind of cloud computing platform |
| CN108241534A (en) * | 2016-12-27 | 2018-07-03 | 阿里巴巴集团控股有限公司 | A kind of task processing, distribution, management, the method calculated and device |
| CN106844027A (en) * | 2017-01-13 | 2017-06-13 | 广西电网有限责任公司电力科学研究院 | A kind of method for scheduling task based on node load |
| CN108664326A (en) * | 2017-03-28 | 2018-10-16 | 富士通株式会社 | Information processing equipment and information processing system |
| CN107562537A (en) * | 2017-08-21 | 2018-01-09 | 中南大学 | A kind of cloud computing method for scheduling task based on gravitation search |
| CN107562537B (en) * | 2017-08-21 | 2020-11-06 | 中南大学 | Cloud computing task scheduling method based on universal gravitation search |
| CN110196768B (en) * | 2018-03-22 | 2022-10-28 | 腾讯科技（深圳）有限公司 | Method and device for automatically determining load degree of cloud platform resources |
| CN110196768A (en) * | 2018-03-22 | 2019-09-03 | 腾讯科技（深圳）有限公司 | The method and apparatus for automatically determining the loading level of cloud platform resource |
| CN109445918A (en) * | 2018-10-17 | 2019-03-08 | Oppo广东移动通信有限公司 | Method for scheduling task, device, terminal and storage medium |
| CN109614228A (en) * | 2018-11-27 | 2019-04-12 | 南京轨道交通系统工程有限公司 | Comprehensively monitoring front-end system and working method based on dynamic load leveling mode |
| CN110348681B (en) * | 2019-06-04 | 2022-02-18 | 国网浙江省电力有限公司衢州供电公司 | Power CPS dynamic load distribution method |
| CN110348681A (en) * | 2019-06-04 | 2019-10-18 | 国网浙江省电力有限公司衢州供电公司 | A kind of electric power CPS dynamic load distribution method |
| CN110365765A (en) * | 2019-07-11 | 2019-10-22 | 网宿科技股份有限公司 | A kind of bandwidth scheduling method and device of cache server |
| CN112738146A (en) * | 2019-10-28 | 2021-04-30 | 杭州海康威视系统技术有限公司 | Access node equipment, access system, equipment scheduling method and equipment scheduling device |
| CN112738146B (en) * | 2019-10-28 | 2022-07-05 | 杭州海康威视系统技术有限公司 | Access node equipment, access system, equipment scheduling method and equipment scheduling device |
| CN112835773B (en) * | 2019-11-25 | 2023-08-11 | 合肥欣奕华智能机器股份有限公司 | Method and device for evaluating task running instantaneity in operating system |
| CN112835773A (en) * | 2019-11-25 | 2021-05-25 | 合肥欣奕华智能机器有限公司 | Method and device for evaluating real-time performance of task running in operating system |
| CN111711575A (en) * | 2020-03-18 | 2020-09-25 | 宁波送变电建设有限公司永耀科技分公司 | Distributed multi-station fusion system fault diagnosis and flow dynamic scheduling method |
| CN112003660B (en) * | 2020-07-17 | 2022-03-18 | 北京大学深圳研究生院 | Dimension measurement method of resources in network, calculation force scheduling method and storage medium |
| CN112003660A (en) * | 2020-07-17 | 2020-11-27 | 北京大学深圳研究生院 | Dimension measurement method of resources in network, calculation force scheduling method and storage medium |
| CN112035236A (en) * | 2020-09-08 | 2020-12-04 | 深圳天源迪科信息技术股份有限公司 | Task scheduling method, device and storage medium based on multi-factor cooperation |
| CN112035236B (en) * | 2020-09-08 | 2023-02-14 | 深圳天源迪科信息技术股份有限公司 | Task scheduling method, device and storage medium based on multi-factor cooperation |
| CN112788099A (en) * | 2020-11-11 | 2021-05-11 | 中移雄安信息通信科技有限公司 | Method, device and equipment for loading back-end service and computer storage medium |
| CN112328383A (en) * | 2020-11-19 | 2021-02-05 | 湖南智慧畅行交通科技有限公司 | Priority-based job concurrency control and scheduling algorithm |
| CN112394803B (en) * | 2020-11-25 | 2023-01-24 | 超越科技股份有限公司 | Domestic server power consumption real-time dynamic adjusting method |
| CN112394803A (en) * | 2020-11-25 | 2021-02-23 | 超越科技股份有限公司 | Domestic server power consumption real-time dynamic adjusting method |
| CN113159957A (en) * | 2021-05-17 | 2021-07-23 | 深圳前海微众银行股份有限公司 | Transaction processing method and device |
| CN113434267A (en) * | 2021-05-25 | 2021-09-24 | 深圳大学 | Cloud computing workflow dynamic scheduling method, device, equipment and storage medium |
| CN113434267B (en) * | 2021-05-25 | 2022-12-02 | 深圳大学 | Cloud computing workflow dynamic scheduling method, device, equipment and storage medium |
| CN116151137A (en) * | 2023-04-24 | 2023-05-23 | 之江实验室 | Simulation system, method and device |
| CN116341991A (en) * | 2023-05-29 | 2023-06-27 | 江苏智慧优视电子科技有限公司 | Heavy-duty truck power conversion cloud service system and method based on cloud computing |
| CN116341991B (en) * | 2023-05-29 | 2023-08-18 | 江苏智慧优视电子科技有限公司 | Heavy-duty truck power conversion cloud service system and method based on cloud computing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102708011B (en) | 2014-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102708011B (en) | Adaptive task scheduling method of cloud computing platform | |
| CN110096349B (en) | Job scheduling method based on cluster node load state prediction | |
| CN102111337B (en) | Method and system for task scheduling | |
| CN103327072B (en) | A kind of method of cluster load balance and system thereof | |
| CN106250305B (en) | The self-adaptation control method of monitoring system data collection cycle under cloud computing environment | |
| CN101488098B (en) | Multi-core computing resource management system based on virtual computing technology | |
| CN103699433B (en) | One kind dynamically adjusts number of tasks purpose method and system in Hadoop platform | |
| CN110413389A (en) | A kind of task schedule optimization method under the unbalanced Spark environment of resource | |
| EP2362297A1 (en) | Technique for selecting a frequency of operation in a processor system | |
| CN105302638A (en) | MPP (Massively Parallel Processing) cluster task scheduling method based on system load | |
| CN110099083A (en) | A kind of load equilibration scheduling method and device for server cluster | |
| Mao et al. | A load-driven task scheduler with adaptive DSC for MapReduce | |
| Li et al. | Adaptive priority-based data placement and multi-task scheduling in geo-distributed cloud systems | |
| CN115718644A (en) | Computing task cross-region migration method and system for cloud data center | |
| Li et al. | Dynamic load balancing algorithm based on FCFS | |
| CN105393518B (en) | Distributed cache control method and device | |
| Jiang et al. | An energy-aware virtual machine migration strategy based on three-way decisions | |
| CN105740077B (en) | Task allocation method suitable for cloud computing | |
| CN115858155A (en) | Dynamic capacity expansion and contraction method and device for application resources of computing power network platform | |
| CN113342460B (en) | Energy consumption control method for cloud data center facing burst load | |
| Li et al. | A live migration strategy for virtual machine based on performance predicting | |
| CN114741200A (en) | Data center station-oriented computing resource allocation method and device and electronic equipment | |
| Kishore et al. | Qos aware resource management for apache cassandra | |
| CN105069250A (en) | Task priority calculation method based on scheduling granularity | |
| CN113391928B (en) | Hardware resource allocation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20160309 Address after: 210046 Jiangsu Province Economic and Technological Development Zone Nanjing Xing Zhi road Xingzhi Science Park building B room 0910 Patentee after: Nanjing Dunhua Traffic Technology Co., Ltd. Address before: 210003 Nanjing City, Jiangsu Province, the new model road No. 66 Patentee before: Nanjing Post & Telecommunication Univ. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140326 Termination date: 20180511 |